Oreilly – AI Security and Responsible AI Practices 2024-3

Course details

• Publisher: Oreilly
• Instructor: Omar Santos , Dr. Petar Radanliev
• Training level: beginner to advanced
• Training duration: 4 hours 55 minutes

Course headings

• Introduction
  1. AI Security and Responsible AI Practices: Introduction
• Module 1: Fundamentals of AI and ML
  1. Module introduction
• Lesson 1: Overview of AI and ML Implementations
  1. Learning objectives
  2. 1.1 Delving into supervised, unsupervised, and reinforcement learning
  3. 1.2 Diving into applications and use cases
  4. 1.3 Strategies in preprocessing and feature engineering
  5. 1.4 Navigating through popular and traditional ML algorithms
  6. 1.5 Exploring model evaluation and validation
• Lesson 2: Generative AI and Large Language Models (LLMs)
  1. Learning objectives
  2. 2.1 Introduction to generative AI
  3. 2.2 Delving into large language models (LLMs)
  4. 2.3 Exploring examples of AI applications we use on a daily basis
  5. 2.4 Going beyond ChatGPT, MidJourney, LLaMA
  6. 2.5 Exploring Hugging Face, LangChain Hub, and other AI model and dataset sharing hubs
  7. 2.6 Modern AI model training environments
  8. 2.7 Introducing LangChain, templates, and agents
  9. 2.8 Fine tuning AI Models using LoRA and QLoRA
  10. 2.9 Introducing retrieval-augmented generation (RAG)
• Module 2: AI and ML Security
  1. Module introduction
• Lesson 3: Fundamentals of AI and ML Security
  1. Learning objectives
  2. 3.1 Importance of security in AI and ML systems
  3. 3.2 OWASP top 10 risks for LLM applications
  4. 3.3 Exploring prompt injection attacks
  5. 3.4 Surveying data poisoning attacks
  6. 3.5 Understanding insecure output handling
  7. 3.6 Discussing insecure plugin design
  8. 3.7 Understanding excessive agency
  9. 3.8 Exploring model theft attacks
  10. 3.9 Understanding overreliance of AI systems
• Lesson 4: How Attackers Are Using AI to Perform Attacks
  1. Learning objectives
  2. 4.1 Exploring the MITRE ATLAS framework
  3. 4.2 AI supply chain security
  4. 4.3 Automated vulnerability discovery and creating exploits at scale
  5. 4.4 Intelligent data harvesting, OSINT, automating phishing, and social engineering attacks
  6. 4.5 Exploring examples of deepfakes and synthetic media
  7. 4.6 Dynamic obfuscation of attack vectors
• Lesson 5: AI System and Infrastructure Security
  1. Learning objectives
  2. 5.1 Secure development practices
  3. 5.2 Monitoring and auditing
  4. 5.3 Software Bill of Materials (SBOMs) and AI Bill of Materials (AI BOMs)
  5. 5.4 Using CSAF and VEX to accelerate vulnerability management
• Module 3: Privacy and Ethical Considerations
  1. Module introduction
• Lesson 6: Privacy and AI Fundamentals
  1. Learning objectives
  2. 6.1 Understanding key privacy considerations in AI implementations
  3. 6.2 Bias and fairness in AI and ML systems
  4. 6.3 Transparency and accountability
  5. 6.4 Understanding differential privacy
  6. 6.5 Exploring secure multi-party computation (SMPC)
  7. 6.6 Understanding homomorphic encryption
  8. 6.7 Understanding the AI data lifecycle management
  9. 6.8 Delving into federated learning
• Lesson 7: AI Ethics
  1. Learning objectives
  2. 7.1 Ethical considerations in AI development
  3. 7.2 Responsible AI frameworks
  4. 7.3 Policy frameworks
  5. 7.4 Exploring strategies to mitigate bias
• Lesson 8: Legal and Regulatory Compliance
  1. Learning objectives
  2. 8.1 Overview of upcoming regulations and guidelines
  3. 8.2 Ensuring compliance in AI and ML systems
  4. 8.3 Case studies and best practices
• Summary
  1. AI Security and Responsible AI Practices: Summary

Images of AI Security and Responsible AI Practices course

Sample video of the course

download link

Download part 1 – 1 GB

Download part 2 – 289 MB

File(s) password: www.downloadly.ir

Size

1.2 GB